© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 69830
    Prev
    Next
    INDEX
    Explanations

    terms related to processes of analysis, improvement, and development in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orf
    -0.08
    endar
    -0.07
    uba
    -0.07
    æı
    -0.07
    undles
    -0.07
    ãĢģãĢģ
    -0.06
    ãĥ«ãĥķ
    -0.06
    hum
    -0.06
    geç
    -0.06
    kek
    -0.06
    POSITIVE LOGITS
    744
    0.07
    edException
    0.07
     capability
    0.07
    άÏģ
    0.07
    edBy
    0.06
     capabilities
    0.06
    930
    0.06
    AGE
    0.06
    ment
    0.06
    780
    0.06
    Activations Density 0.278%

    No Known Activations